Model Peramalan Indeks Harga Konsumen Kota Palangka Raya Menggunakan Seasonal ARIMA (SARIMA)
Abstract
Forecasting Model for Consumer Price Index of Palangka Raya City
using Seasonal ARIMA (SARIMA)
Abstrak. Palangka Raya merupakan salah kota indikator perhitungan Indeks Harga Konsumen (IHK) di Provinsi Kalimantan Tengah. Secara tidak langsung, persentase perubahan IHK, senantiasa dijaga oleh pemerintah agar tetap rendah dan stabil untuk prasyarat pertumbuhan ekonomi berkesinambungan serta mampu memberikan manfaat bagi peningkatan kesejahteraan masyarakat. Oleh karena itu, peramalan data IHK perlu dilakukan untuk membantu pemerintah dalam menyusun suatu kebijakan. Salah satu metode statistik yang paling tepat untuk melakukan peramalan data IHK Kota Palangka Raya dengan menggunakan Seasonal Autoregressive Integrated Moving Average (SARIMA). Metode SARIMA sangat cocok untuk diterapkan pada data IHK karena terdapat pola musiman yang terjadi pada waktu tertentu. Data yang digunakan merupakan data sekunder bersumber dari Badan Pusat Statistik (BPS) Provinsi Kalimantan Tengah dengan series sebanyak 48 observasi. Berdasarkan hasil trial and error, model SARIMA pada saat , dan dianggap sebagai model terbaik untuk peramalan data IHK dengan koefisien determinasi adjusted sebesar 84,67%. Selain itu, model peramalan memenuhi seluruh uji asumsi diagnostik dan sangat powerful mendekati data aktual.
Kata kunci: SARIMA, Peramalan, IHK
Abstract. Palangka Raya is one of the indicator city for Consumer Price Index (CPI) calculation in Central Kalimantan Province. The percentage of changes in CPI had always been indirectly maintained by government in order to remain low and stable as a preconditions for sustainable economic growth and to provide benefits for improving people's walfare. Therefore, the forecasting of CPI is required to assist the development of government's policy. One of the precise statistical method for forecasting Palangka Raya's CPI is Seasonal Autoregressive Integrated Moving Average (SARIMA). SARIMA is very suitable to be applied in Consumer Price Index's data because of seasonal patterns that occured in several times. The data used in this research are secondary data sourced from Statistics Indonesia of Central Kalimantan Office with 48 observations. Based on trial and error process, SARIMA when , is considered the best statistical model to forecast CPI data with an adjusted coefficent of determination 84.67%. This forecasting model also fulfilled all diagnostic assumptions' tests and powerfully approached the actual data.
Keywords: SARIMA, Forcasting, CPI
Full Text:
PDF (Bahasa Indonesia)References
Ardhikari, A. & Agrawal, R. K., An Introductory Study on Time Series Modeling and Forecasting. CoRR, abs/1302.6613, 2013
Badan Pusat Statistik, Indeks Harga Konsumen Kota Palangka Raya. [Alamat url diakses 2017]. https://kalteng.bps.go.id/statictable/2017/07/07/443/indeks-harga-konsumen-kota-palangka-raya-1996-2017.html.
Bank Indonesia, Pengenalan Inflasi. [diakses 31 Juli 2018]. https://www.bi.go.id/id/moneter/inflasi/ pengenalan/Contents/Pentingnya.aspx.
Brockwell J. P. & Davis R. A., Introdution to Time Series and Forecasting. New York: Springer. 2002.
Baumöhl E. & Lyócsa S., Stationarity of Time Series and the Problem of Spurious Regression. MPRA Paper 27926, University Library of Munich, Germany. 2009.
Gikungu S. W., Waititu A. G., Kihoro J. M., Forecasting inflation rate in Kenya using SARIMA model. American Journal of Theoretical and Applied Statistics. 2015.
Octavia T., Yulia, Lydia, Peramalan Stok Barang untuk Membantu Pengambilan Keputusan Pembelian Barang Pada Toko Bangunan XYZ dengan Metode Arima. Seminar Nasional Informatika, 2013.
Suseno & Aisyah, S., Inflasi, Jakarta: Bank Indonesia, 2009.
DOI: https://doi.org/10.29313/jmtm.v17i2.3981
Refbacks
- There are currently no refbacks.
Copyright (c) 2018 Matematika
ISSN : 1412-5056 | E-ISSN 2598-8980
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Indexed by: